© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35573
    Prev
    Next
    INDEX
    Explanations

    items related to coding, software development, and computer programming

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    167
    +0.08
    0.5%
    593
    +0.08
    0.5%
    386
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    154
    +0.08
    0.11
    338
    +0.08
    0.08
    634
    +0.08
    0.09
    Negative Logits
    aido
    -0.63
    ¶ħ
    -0.59
     Labrador
    -0.56
    iceps
    -0.56
     graz
    -0.55
    kered
    -0.52
    ascus
    -0.52
    orthy
    -0.51
    icz
    -0.50
    ffield
    -0.50
    POSITIVE LOGITS
    LOG
    0.75
     Alphabet
    0.64
    EMOTE
    0.61
    forth
    0.61
     Opera
    0.60
     Entity
    0.59
    },{"
    0.57
    SAY
    0.57
     PsyNet
    0.57
    VERTISEMENT
    0.56
    Activations Density 6.516%

    No Known Activations